{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:11:31Z","timestamp":1782886291030,"version":"3.54.5"},"reference-count":245,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T00:00:00Z","timestamp":1776297600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2022NSCQ-MSX0837"],"award-info":[{"award-number":["CSTB2022NSCQ-MSX0837"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2024NSCQ-LZX0080"],"award-info":[{"award-number":["CSTB2024NSCQ-LZX0080"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2023NSCQ-LZX0068"],"award-info":[{"award-number":["CSTB2023NSCQ-LZX0068"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2025NSCQ-LZX0115"],"award-info":[{"award-number":["CSTB2025NSCQ-LZX0115"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005230","name":"Natural Science Foundation of Chongqing Municipality","doi-asserted-by":"publisher","award":["CSTB2023TIAD-STX0020"],"award-info":[{"award-number":["CSTB2023TIAD-STX0020"]}],"id":[{"id":"10.13039\/501100005230","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471075"],"award-info":[{"award-number":["62471075"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012669","name":"Natural Science Foundation Project of Chongqing","doi-asserted-by":"publisher","award":["YJX-2025001001002"],"award-info":[{"award-number":["YJX-2025001001002"]}],"id":[{"id":"10.13039\/501100012669","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.inffus.2026.104386","type":"journal-article","created":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:47:10Z","timestamp":1776354430000},"page":"104386","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["Medical multimodal large language models: A survey"],"prefix":"10.1016","volume":"134","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4359-7455","authenticated-orcid":false,"given":"Hanguang","family":"Xiao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5231-8955","authenticated-orcid":false,"given":"Ningzhi","family":"Hui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0530-2123","authenticated-orcid":false,"given":"Yong","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3997-5991","authenticated-orcid":false,"given":"Zhipeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jincheng","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104386_bib0001","unstructured":"A. Hurst, A. Lerer, A. P. Goucher, A. Perelman, A. Ramesh, A. Clark, A. J. Ostrow, A. Welihinda, A. Hayes, A. Radford, et al., Gpt-4o system card, arXiv preprint arXiv: 2410.21276(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0002","unstructured":"S. Bai, Y. Cai, R. Chen, K. Chen, X. Chen, Z. Cheng, L. Deng, W. Ding, C. Gao, C. Ge, et al., Qwen3-vl technical report, arXiv preprint arXiv: 2511.21631(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0003","first-page":"34892","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0004","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0005","series-title":"Machine Learning for Health (ML4H)","first-page":"353","article-title":"Med-flamingo: a multimodal medical few-shot learner","author":"Moor","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0006","unstructured":"A. Awadalla, I. Gao, J. Gardner, J. Hessel, Y. Hanafy, W. Zhu, K. Marathe, Y. Bitton, S. Gadre, S. Sagawa, et al., OpenFlamingo: an open-source framework for training large autoregressive vision-language models, arXiv preprint arXiv: 2308.01390(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0007","first-page":"28541","article-title":"LLaVA-med: training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0008","unstructured":"Y. Ye, Z. Huang, Y. Xiao, E. Chern, S. Xia, P. Liu, LIMO: less is more for reasoning, arXiv preprint arXiv: 2502.03387(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0009","unstructured":"S.S. Mullappilly, M.I. Kurpath, O. Mohamed, M. Zidan, F. Khan, S. Khan, R. Anwer, H. Cholakkal, MediX-R1: open ended medical reinforcement learning, arXiv preprint arXiv: 2602.23363(2026)."},{"key":"10.1016\/j.inffus.2026.104386_bib0010","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.inffus.2026.104386_bib0011","doi-asserted-by":"crossref","first-page":"94","DOI":"10.3390\/fi13040094","article-title":"Privacy preserving machine learning with homomorphic encryption and federated learning","volume":"13","author":"Fang","year":"2021","journal-title":"Future Internet"},{"issue":"22","key":"10.1016\/j.inffus.2026.104386_bib0012","doi-asserted-by":"crossref","first-page":"46316","DOI":"10.1109\/JIOT.2025.3605040","article-title":"Quantum computing and the future of healthcare internet of things security: challenges and opportunities","volume":"12","author":"Adil","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"9","key":"10.1016\/j.inffus.2026.104386_bib0013","doi-asserted-by":"crossref","first-page":"8189","DOI":"10.21037\/qims-2025-824","article-title":"YOLOv8-BCD: A real-time deep learning framework for pulmonary nodule detection in computed tomography imaging","volume":"15","author":"Zhu","year":"2025","journal-title":"Quant. Imaging Med. Surg."},{"key":"10.1016\/j.inffus.2026.104386_bib0014","doi-asserted-by":"crossref","DOI":"10.3389\/fradi.2025.1616293","article-title":"Brain tumor segmentation using deep learning: high performance with minimized MRI data","volume":"5","author":"Huang","year":"2025","journal-title":"Front. Radiol."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0015","doi-asserted-by":"crossref","first-page":"3763","DOI":"10.1038\/s41598-025-87171-9","article-title":"A deep learning based model for diabetic retinopathy grading","volume":"15","author":"Akhtar","year":"2025","journal-title":"Sci. Rep."},{"issue":"5","key":"10.1016\/j.inffus.2026.104386_bib0016","doi-asserted-by":"crossref","DOI":"10.1016\/j.heliyon.2024.e27200","article-title":"An arrhythmia classification approach via deep learning using single-lead ECG without QRS wave detection","volume":"10","author":"Liu","year":"2024","journal-title":"Heliyon"},{"issue":"11","key":"10.1016\/j.inffus.2026.104386_bib0017","doi-asserted-by":"crossref","first-page":"3129","DOI":"10.1038\/s41591-024-03185-2","article-title":"A generalist vision\u2013language foundation model for diverse biomedical tasks","volume":"30","author":"Zhang","year":"2024","journal-title":"Nat. Med."},{"issue":"2","key":"10.1016\/j.inffus.2026.104386_bib0018","doi-asserted-by":"crossref","first-page":"136","DOI":"10.3390\/info16020136","article-title":"A survey on multimodal large language models in radiology for report generation and visual question answering","volume":"16","author":"Yi","year":"2025","journal-title":"Information"},{"issue":"3","key":"10.1016\/j.inffus.2026.104386_bib0019","doi-asserted-by":"crossref","DOI":"10.1056\/AIoa2300138","article-title":"Towards generalist biomedical AI","volume":"1","author":"Tu","year":"2024","journal-title":"NEJM AI"},{"issue":"7956","key":"10.1016\/j.inffus.2026.104386_bib0020","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1038\/s41586-023-05881-4","article-title":"Foundation models for generalist medical artificial intelligence","volume":"616","author":"Moor","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.inffus.2026.104386_bib0021","doi-asserted-by":"crossref","DOI":"10.2196\/59505","article-title":"Multimodal large language models in health care: applications, challenges, and future outlook","volume":"26","author":"AlSaad","year":"2024","journal-title":"J. Med. Internet Res."},{"issue":"10","key":"10.1016\/j.inffus.2026.104386_bib0022","doi-asserted-by":"crossref","first-page":"900","DOI":"10.3348\/kjr.2025.0599","article-title":"Multimodal large language models in medical imaging: current state and future directions","volume":"26","author":"Nam","year":"2025","journal-title":"Korean J. Radiol."},{"key":"10.1016\/j.inffus.2026.104386_bib0023","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102888","article-title":"A comprehensive survey of large language models and multimodal large language models in medicine","volume":"117","author":"Xiao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104386_bib0024","series-title":"Proceedings of the 23rd Workshop on Biomedical Natural Language Processing","first-page":"440","article-title":"XrayGPT: chest radiographs summarization using large medical vision-language models","author":"Thawakar","year":"2024"},{"issue":"3","key":"10.1016\/j.inffus.2026.104386_bib0025","doi-asserted-by":"crossref","DOI":"10.1016\/j.metrad.2023.100033","article-title":"R2genGPT: Radiology report generation with frozen llms","volume":"1","author":"Wang","year":"2023","journal-title":"Meta Radiol."},{"key":"10.1016\/j.inffus.2026.104386_bib0026","doi-asserted-by":"crossref","DOI":"10.2196\/32690","article-title":"Vision-language model for generating textual descriptions from clinical images: model development and validation study","volume":"8","author":"Ji","year":"2024","journal-title":"JMIR Formative Res."},{"key":"10.1016\/j.inffus.2026.104386_bib0027","series-title":"Proceedings of the 23rd Workshop on Biomedical Natural Language Processing","first-page":"597","article-title":"MAIRA at RRG24: a specialised large multimodal model for radiology report generation","author":"Srivastav","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0028","unstructured":"Z. Zhou, M. Shi, M. Wei, O. Alabi, Z. Yue, T. Vercauteren, Large model driven radiology report generation with clinical quality reinforcement learning, arXiv preprint arXiv: 2403.06728(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0029","unstructured":"Z. Chen, M. Varma, J. Xu, M. Paschali, D. Van Veen, A. Johnston, A. Youssef, L. Blankemeier, C. Bluethgen, S. Altmayer, et al., A vision-language foundation model to enhance efficiency of chest X-ray interpretation, arXiv preprint arXiv: 2401.12208(2024)."},{"key":"10.1016\/j.inffus.2026.104386_sbref0030","article-title":"XrayGLM: the first chinese medical multimodal model that chest radiographs summarization","author":"Wang","year":"2023","journal-title":"GitHub repository"},{"key":"10.1016\/j.inffus.2026.104386_bib0031","unstructured":"Q. Miao, K. Liu, Z. Ma, Y. Li, X. Kang, R. Liu, T. Liu, K. Xie, Z. Jiao, Evoke: elevating chest x-ray report generation via multi-view contrastive learning and patient-specific knowledge, arXiv preprint arXiv: 2411.10224(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0032","series-title":"International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"726","article-title":"Open-ended medical visual question answering through prefix tuning of language models","author":"Van Sonsbeek","year":"2023"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0033","doi-asserted-by":"crossref","first-page":"7866","DOI":"10.1038\/s41467-025-62385-7","article-title":"Towards generalist foundation model for radiology by leveraging web-scale 2D&3D medical data","volume":"16","author":"Wu","year":"2025","journal-title":"Nat. Commun."},{"key":"10.1016\/j.inffus.2026.104386_bib0034","unstructured":"B. Yang, A. Raza, Y. Zou, T. Zhang, Customizing general-purpose foundation models for medical report generation, arXiv preprint arXiv: 2306.05642(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0035","unstructured":"K. Saab, T. Tu, W.-H. Weng, R. Tanno, D. Stutz, E. Wulczyn, F. Zhang, T. Strother, C. Park, E. Vedadi, et al., Capabilities of gemini models in medicine, arXiv preprint arXiv: 2404.18416(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0036","series-title":"International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"374","article-title":"Masked vision and language pre-training with unimodal and multimodal contrastive losses for medical visual question answering","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0037","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4971","article-title":"LaPA: latent prompt assist model for medical visual question answering","author":"Gu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0038","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"3843","article-title":"Med-MoE: mixture of domain-specific experts for lightweight medical vision-language models","author":"Jiang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2025.104849","article-title":"SigPhi-Med: a lightweight vision-language assistant for biomedicine","volume":"167","author":"Zhou","year":"2025","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.inffus.2026.104386_bib0040","unstructured":"Y. Xie, C. Zhou, L. Gao, J. Wu, X. Li, H.-Y. Zhou, S. Liu, L. Xing, J. Zou, C. Xie, et al., MedTrinity-25M: a large-scale multimodal dataset with multigranular annotations for medicine, arXiv preprint arXiv: 2408.02900(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0041","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"3779","article-title":"Towards a multimodal large language model with pixel-level insight for biomedicine","volume":"39","author":"Huang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0042","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1439","article-title":"Generating radiology reports via memory-driven transformer","author":"Chen","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0043","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11Th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"5904","article-title":"Cross-modal memory networks for radiology report generation","author":"Chen","year":"2021"},{"key":"10.1016\/j.inffus.2026.104386_bib0044","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102633","article-title":"Improving chest X-ray report generation by leveraging warm starting","volume":"144","author":"Nicolson","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0045","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11558","article-title":"METransFormer: radiology report generation by transformer with multiple learnable expert tokens","author":"Wang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0046","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"19809","article-title":"KiUT: knowledge-injected U-transformer for radiology report generation","author":"Huang","year":"2023"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0047","doi-asserted-by":"crossref","first-page":"50","DOI":"10.3390\/biomedinformatics4010004","article-title":"Survey of multimodal medical question answering","volume":"4","author":"Demirhan","year":"2023","journal-title":"BioMedInformatics"},{"key":"10.1016\/j.inffus.2026.104386_bib0048","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2023.102611","article-title":"Medical visual question answering: a survey","volume":"143","author":"Lin","year":"2023","journal-title":"Artif. Intell. Med."},{"issue":"5","key":"10.1016\/j.inffus.2026.104386_bib0049","doi-asserted-by":"crossref","first-page":"1532","DOI":"10.1109\/TMI.2022.3232411","article-title":"Medical visual question answering via conditional reasoning and contrastive learning","volume":"42","author":"Liu","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104386_bib0050","doi-asserted-by":"crossref","unstructured":"X. He, Y. Zhang, L. Mou, E. Xing, P. Xie, PathVQA: 30000+ questions for medical visual question answering, arXiv preprint arXiv: 2003.10286(2020).","DOI":"10.36227\/techrxiv.13127537.v1"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0051","doi-asserted-by":"crossref","first-page":"277","DOI":"10.1038\/s43856-024-00709-2","article-title":"Development of a large-scale medical visual question-answering dataset","volume":"4","author":"Zhang","year":"2024","journal-title":"Commun. Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0052","doi-asserted-by":"crossref","DOI":"10.3389\/frai.2024.1430984","article-title":"Vision-language models for medical report generation and visual question answering: a review","volume":"7","author":"Hartsock","year":"2024","journal-title":"Front. Artif. Intell."},{"key":"10.1016\/j.inffus.2026.104386_bib0053","series-title":"Proceedings of the 6th Clinical Natural Language Processing Workshop","first-page":"339","article-title":"MediFact at MEDIQA-M3G 2024: medical question answering in dermatology with multimodal learning","author":"Saeed","year":"2024"},{"issue":"6","key":"10.1016\/j.inffus.2026.104386_bib0054","doi-asserted-by":"crossref","first-page":"2983","DOI":"10.3390\/app15062983","article-title":"Generative models in medical visual question answering: a survey","volume":"15","author":"Dong","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.inffus.2026.104386_bib0055","unstructured":"H. Zhou, F. Liu, B. Gu, X. Zou, J. Huang, J. Wu, Y. Li, S.S. Chen, P. Zhou, J. Liu, et al., A survey of large language models in medicine: progress, application, and challenge, arXiv preprint arXiv: 2311.05112(2023)."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0056","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1038\/s41597-019-0322-0","article-title":"MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports","volume":"6","author":"Johnson","year":"2019","journal-title":"Sci. Data"},{"key":"10.1016\/j.inffus.2026.104386_bib0057","series-title":"International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"210","article-title":"Contrastive pre-training and representation distillation for medical visual question answering based on radiology images","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104386_bib0058","series-title":"International Conference on Information Processing in Medical Imaging","first-page":"445","article-title":"Q2ATransformer: Improving medical VQA via an answer querying decoder","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0059","series-title":"Findings of the Association for Computational Linguistics: EACL 2023","first-page":"1181","article-title":"PubMedCLIP: how much does clip benefit visual question answering in the medical domain?","author":"Eslami","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0060","unstructured":"S. Zhang, Y. Xu, N. Usuyama, H. Xu, J. Bagga, R. Tinn, S. Preston, R. Rao, M. Wei, N. Valluri, et al., BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs, arXiv preprint arXiv: 2303.00915(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0061","series-title":"2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)","first-page":"1","article-title":"Self-supervised vision-language pretraining for medial visual question answering","author":"Li","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0062","doi-asserted-by":"crossref","first-page":"981","DOI":"10.1109\/JBHI.2024.3505955","article-title":"BioMedGPT: an open multimodal large language model for biomedicine","volume":"30","author":"Luo","year":"2024","journal-title":"IEEE J. Biomed. Health Inf."},{"key":"10.1016\/j.inffus.2026.104386_bib0063","series-title":"Proceedings of the 28th International Conference on Computational Linguistics","first-page":"2322","article-title":"Curious case of language generation evaluation metrics: a cautionary tale","author":"Caglayan","year":"2020"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0064","doi-asserted-by":"crossref","DOI":"10.1038\/sdata.2018.251","article-title":"A dataset of clinically generated visual questions and answers about radiology images","volume":"5","author":"Lau","year":"2018","journal-title":"Sci. Data"},{"key":"10.1016\/j.inffus.2026.104386_bib0065","series-title":"2021 IEEE 18th International Symposium on Biomedical Imaging (ISBI)","first-page":"1650","article-title":"SLAKE: a semantically-labeled knowledge-enhanced dataset for medical visual question answering","author":"Liu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104386_bib0066","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"374","article-title":"Green: generative radiology report evaluation and error notation","author":"Ostmeier","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0067","series-title":"Thirty-Fourth International Joint Conference on Artificial Intelligence (IJCAI-25)","article-title":"Localizing before answering: a benchmark for grounded medical visual question answering","author":"Nguyen","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0068","series-title":"International Conference on Medical Image Computing and Computer Assisted Intervention","first-page":"325","article-title":"Knowing or guessing? Robust medical visual question answering via joint consistency and contrastive learning","author":"Jiang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0069","series-title":"2023 IEEE International Conference on Big Data (BigData)","first-page":"2247","article-title":"Multimodal large language models: a survey","author":"Wu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0070","series-title":"Proceedings of the Asian Conference on Computer Vision","first-page":"2404","article-title":"MedBLIP: bootstrapping language-image pre-training from 3d medical images and texts","author":"Chen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0071","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0072","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.inffus.2026.104386_bib0073","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.inffus.2026.104386_bib0074","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: transformers for image recognition at scale, arXiv preprint arXiv: 2010.11929(2020)."},{"key":"10.1016\/j.inffus.2026.104386_bib0075","series-title":"Machine Learning for Healthcare Conference","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","author":"Zhang","year":"2022"},{"key":"10.1016\/j.inffus.2026.104386_bib0076","unstructured":"M. Oquab, T. Darcet, T. Moutakanni, H. Vo, M. Szafraniec, V. Khalidov, P. Fernandez, D. Haziza, F. Massa, A. El-Nouby, et al., DINOv2: learning robust visual features without supervision, arXiv preprint arXiv: 2304.07193(2023)."},{"issue":"3","key":"10.1016\/j.inffus.2026.104386_bib0077","doi-asserted-by":"crossref","first-page":"940","DOI":"10.1109\/TCBB.2019.2939522","article-title":"D-UNet: a dimension-fusion U shape network for chronic stroke lesion segmentation","volume":"18","author":"Zhou","year":"2019","journal-title":"IEEE\/ACM Trans. Comput. Biol. Bioinf."},{"key":"10.1016\/j.inffus.2026.104386_bib0078","unstructured":"J. Lahoud, J. Cao, F.S. Khan, H. Cholakkal, R.M. Anwer, S. Khan, M.-H. Yang, 3D vision with transformers: a survey, arXiv preprint arXiv: 2208.04309(2022)."},{"key":"10.1016\/j.inffus.2026.104386_bib0079","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2024","first-page":"16449","article-title":"Quantifying and mitigating unimodal biases in multimodal large language models: a causal perspective","author":"Chen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0080","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"4725","article-title":"BSAFusion: a bidirectional stepwise feature alignment network for unaligned medical image fusion","volume":"39","author":"Li","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0081","first-page":"33536","article-title":"Multi-granularity cross-modal alignment for generalized medical visual representation learning","volume":"35","author":"Wang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0082","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"issue":"4\u20135","key":"10.1016\/j.inffus.2026.104386_bib0083","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1016\/j.compmedimag.2007.02.002","article-title":"Computer-aided diagnosis in medical imaging: historical review, current status and future potential","volume":"31","author":"Doi","year":"2007","journal-title":"Comput. Med. Imaging Graph."},{"issue":"5","key":"10.1016\/j.inffus.2026.104386_bib0084","doi-asserted-by":"crossref","first-page":"e218","DOI":"10.1002\/mp.13764","article-title":"Computer-aided diagnosis in the era of deep learning","volume":"47","author":"Chan","year":"2020","journal-title":"Med. Phys."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0085","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1038\/s44172-024-00271-8","article-title":"Interactive computer-aided diagnosis on medical image using large language models","volume":"3","author":"Wang","year":"2024","journal-title":"Commun. Eng."},{"issue":"11","key":"10.1016\/j.inffus.2026.104386_bib0086","doi-asserted-by":"crossref","first-page":"3755","DOI":"10.1109\/TMI.2024.3398350","article-title":"ChatCAD+: toward a universal and reliable interactive CAD using LLMs","volume":"43","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"10.1016\/j.inffus.2026.104386_bib0087","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11137","article-title":"CARZero: cross-attention alignment for radiology zero-shot classification","author":"Lai","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0088","unstructured":"T.-T. Chang, S. Venkataraman, LV-XAttn: distributed cross-attention for long visual inputs in multimodal large language models, arXiv preprint arXiv: 2502.02406(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0089","series-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)","first-page":"540","article-title":"Lost in space: probing fine-grained spatial understanding in vision and language resamplers","author":"Pantazopoulos","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0090","series-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"issue":"4","key":"10.1016\/j.inffus.2026.104386_bib0091","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"BioBERT: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Lee","year":"2020","journal-title":"Bioinformatics"},{"key":"10.1016\/j.inffus.2026.104386_bib0092","series-title":"Proceedings of the 2nd Clinical Natural Language Processing Workshop","first-page":"72","article-title":"Publicly available clinical BERT embeddings","author":"Alsentzer","year":"2019"},{"issue":"12","key":"10.1016\/j.inffus.2026.104386_bib0093","article-title":"Benchmarking effectiveness and efficiency of deep learning models for semantic textual similarity in the clinical domain: validation study","volume":"9","author":"Chen","year":"2021","journal-title":"JMIR Med. Inf."},{"key":"10.1016\/j.inffus.2026.104386_bib0094","series-title":"Proceedings of the 18th BioNLP Workshop and Shared Task","first-page":"58","article-title":"Transfer learning in biomedical natural language processing: an evaluation of BERT and ELMo on ten benchmarking datasets","author":"Peng","year":"2019"},{"key":"10.1016\/j.inffus.2026.104386_bib0095","unstructured":"A. Grattafiori, A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Vaughan, et al., The llama 3 herd of models, arXiv preprint arXiv: 2407.21783(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0096","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"10859","article-title":"Huatuogpt, towards taming language model to be a doctor","author":"Zhang","year":"2023"},{"issue":"140","key":"10.1016\/j.inffus.2026.104386_bib0097","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104386_bib0098","series-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","first-page":"7871","article-title":"BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0099","doi-asserted-by":"crossref","DOI":"10.3389\/fdata.2024.1371680","article-title":"MedT5SQL: a transformers-based large language model for text-to-SQL conversion in the healthcare domain","volume":"7","author":"Marshan","year":"2024","journal-title":"Front. Big Data"},{"key":"10.1016\/j.inffus.2026.104386_bib0100","series-title":"Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 2020","article-title":"A multilingual neural machine translation model for biomedical data","author":"B\u00e9rard","year":"2020"},{"issue":"120","key":"10.1016\/j.inffus.2026.104386_bib0101","first-page":"1","article-title":"Switch transformers: scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.inffus.2026.104386_bib0102","unstructured":"G. Hinton, O. Vinyals, J. Dean, Distilling the knowledge in a neural network, arXiv preprint arXiv: 1503.02531(2015)."},{"key":"10.1016\/j.inffus.2026.104386_bib0103","unstructured":"H. Chen, R. Chen, Y. Yi, X. Quan, C. Li, M. Yan, J. Zhang, Knowledge distillation of black-box large language models, arXiv preprint arXiv: 2401.07013(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0104","unstructured":"Y. Gu, L. Dong, F. Wei, M. Huang, MiniLLM: knowledge distillation of large language models, arXiv preprint arXiv: 2306.08543(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0105","unstructured":"V. Sanh, L. Debut, J. Chaumond, T. Wolf, DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter, arXiv preprint arXiv: 1910.01108(2019)."},{"key":"10.1016\/j.inffus.2026.104386_bib0106","unstructured":"X. Xu, M. Li, C. Tao, T. Shen, R. Cheng, J. Li, C. Xu, D. Tao, T. Zhou, A survey on knowledge distillation of large language models, arXiv preprint arXiv: 2402.13116(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0107","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2704","article-title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference","author":"Jacob","year":"2018"},{"key":"10.1016\/j.inffus.2026.104386_bib0108","unstructured":"M. Sun, Z. Liu, A. Bair, J.Z. Kolter, A simple and effective pruning approach for large language models, arXiv preprint arXiv: 2306.11695(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0109","series-title":"International Conference on Machine Learning","first-page":"10323","article-title":"SparseGPT: massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"11264","article-title":"Importance estimation for neural network pruning","author":"Molchanov","year":"2019"},{"key":"10.1016\/j.inffus.2026.104386_bib0111","unstructured":"J. White, Q. Fu, S. Hays, M. Sandborn, C. Olea, H. Gilbert, A. Elnashar, J. Spencer-Smith, D.C. Schmidt, A prompt pattern catalog to enhance prompt engineering with chatgpt, arXiv preprint arXiv: 2302.11382(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0112","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0113","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"14676","article-title":"Style-aware radiology report generation with radgraph and few-shot prompting","author":"Yan","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0114","unstructured":"A. Huang, O. Banerjee, K. Wu, E.P. Reis, P. Rajpurkar, FineRadScore: a radiology report line-by-line evaluation technique generating corrections with severity scores, arXiv preprint arXiv: 2405.20613(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0115","series-title":"Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)","first-page":"11726","article-title":"Guiding medical vision-language models with diverse visual prompts: framework design and comprehensive exploration of prompt variations","author":"Zhu","year":"2025"},{"issue":"9","key":"10.1016\/j.inffus.2026.104386_bib0116","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae560","article-title":"Biomedical knowledge graph-optimized prompt generation for large language models","volume":"40","author":"Soman","year":"2024","journal-title":"Bioinformatics"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0117","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1038\/s41746-025-01802-z","article-title":"Retrieval-augmented generation elevates local LLM quality in radiology contrast media consultation","volume":"8","author":"Wada","year":"2025","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0118","series-title":"Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering","first-page":"800","article-title":"DeepSearch: a simple and effective blackbox attack for deep neural networks","author":"Zhang","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0119","series-title":"Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing","first-page":"414","article-title":"DeepResearcher: scaling deep research via reinforcement learning in real-world environments","author":"Zheng","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0120","doi-asserted-by":"crossref","first-page":"790","DOI":"10.1038\/s41746-025-02250-5","article-title":"Multi-step retrieval and reasoning improves radiology question answering with large language models","volume":"8","author":"Wind","year":"2025","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0121","doi-asserted-by":"crossref","DOI":"10.3389\/fmed.2025.1716327","article-title":"A self-correcting agentic graph RAG for clinical decision support in hepatology","volume":"12","author":"Hu","year":"2025","journal-title":"Front. Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0122","doi-asserted-by":"crossref","unstructured":"P. Sun, Y. Chen, X. Li, X. Chu, The multi-round diagnostic RAG framework for emulating clinical reasoning, arXiv preprint arXiv: 2504.07724(2025).","DOI":"10.1109\/BIBM66473.2025.11357107"},{"key":"10.1016\/j.inffus.2026.104386_bib0123","unstructured":"Z. Wang, H. Wang, S. Feng, X. Yang, D. Wang, Y. Zhang, J. Lin, H. Yang, X. Ji, DEEPMED: building a medical deepresearch agent via multi-hop med-search data and turn-controlled agentic training & inference, arXiv preprint arXiv: 2601.18496(2026)."},{"key":"10.1016\/j.inffus.2026.104386_bib0124","series-title":"Findings of the Association for Computational Linguistics: EMNLP 2023","first-page":"155","article-title":"On the relation between sensitivity and accuracy in-context learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0125","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: how language models use long contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0126","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"Ma","year":"2024","journal-title":"Nat. Commun."},{"key":"10.1016\/j.inffus.2026.104386_bib0127","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"6769","article-title":"Dense passage retrieval for open-domain question answering","author":"Karpukhin","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0128","unstructured":"Y. Dai, G. Wang, Y. Wang, K. Dou, K. Zhou, Z. Zhang, S. Yang, F. Tang, J. Yin, P. Zeng, et al., EviNote-RAG: enhancing RAG models via answer-supportive evidence notes, arXiv preprint arXiv: 2509.00877(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0129","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"7346","article-title":"Towards injecting medical visual knowledge into multimodal LLMs at scale","author":"Chen","year":"2024"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0130","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/sdata.2016.35","article-title":"MIMIC-III, A freely accessible critical care database","volume":"3","author":"Johnson","year":"2016","journal-title":"Sci. Data"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0131","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41597-022-01899-x","article-title":"MIMIC-IV, a freely accessible electronic health record dataset","volume":"10","author":"Johnson","year":"2023","journal-title":"Sci. Data"},{"key":"10.1016\/j.inffus.2026.104386_bib0132","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"590","article-title":"CheXpert: a large chest radiograph dataset with uncertainty labels and expert comparison","volume":"33","author":"Irvin","year":"2019"},{"key":"10.1016\/j.inffus.2026.104386_bib0133","series-title":"Proceedings of the 1st Workshop on NLP for COVID-19 at ACL 2020","first-page":"160","article-title":"CORD-19: The COVID-19 open research dataset","author":"Wang","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0134","unstructured":"J. Liu, Z. Wang, Q. Ye, D. Chong, P. Zhou, Y. Hua, Qilin-Med-VL: towards chinese large vision-language model for general healthcare, arXiv preprint arXiv: 2310.17956(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0135","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"5034","article-title":"PathAsst: a generative foundation ai assistant towards artificial general intelligence of pathology","volume":"38","author":"Sun","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0136","series-title":"AAAI 2024 Spring Symposium on Clinical Foundation Models","article-title":"CheXagent: towards a foundation model for chest x-ray interpretation","author":"Chen","year":"2024"},{"issue":"2","key":"10.1016\/j.inffus.2026.104386_bib0137","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1093\/jamia\/ocv080","article-title":"Preparing a collection of radiology examinations for distribution and retrieval","volume":"23","author":"Demner-Fushman","year":"2016","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"10.1016\/j.inffus.2026.104386_bib0138","doi-asserted-by":"crossref","DOI":"10.1016\/j.media.2020.101797","article-title":"PadChest: a large chest X-ray image dataset with multi-label annotated reports","volume":"66","author":"Bustos","year":"2020","journal-title":"Med. Image Anal."},{"key":"10.1016\/j.inffus.2026.104386_bib0139","unstructured":"Z. Fan, C. Liang, C. Wu, Y. Zhang, Y. Wang, W. Xie, ChestX-reasoner: advancing radiology foundation models with reasoning through step-by-step verification, arXiv preprint arXiv: 2504.20930(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0140","unstructured":"X. He, S. Chen, Z. Ju, X. Dong, H. Fang, S. Wang, Y. Yang, J. Zeng, R. Zhang, R. Zhang, et al., MedDialog: two large-scale medical dialogue datasets, arXiv preprint arXiv: 2004.03329(2020)."},{"key":"10.1016\/j.inffus.2026.104386_bib0141","series-title":"Findings of the Association for Computational Linguistics: NAACL 2025","first-page":"3828","article-title":"Huatuo-26M, a large-scale chinese medical QA dataset","author":"Wang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0142","unstructured":"X. Zhang, C. Wu, Z. Zhao, W. Lin, Y. Zhang, Y. Wang, W. Xie, PMC-VQA: visual instruction tuning for medical visual question answering, arXiv preprint arXiv: 2305.10415(2023)."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0143","doi-asserted-by":"crossref","first-page":"511","DOI":"10.1186\/s12859-019-3119-4","article-title":"A question-entailment approach to question answering","volume":"20","author":"Ben Abacha","year":"2019","journal-title":"BMC Bioinf."},{"issue":"14","key":"10.1016\/j.inffus.2026.104386_bib0144","doi-asserted-by":"crossref","first-page":"6421","DOI":"10.3390\/app11146421","article-title":"What disease does this patient have? a large-scale open domain question answering dataset from medical exams","volume":"11","author":"Jin","year":"2021","journal-title":"Appl. Sci."},{"key":"10.1016\/j.inffus.2026.104386_bib0145","series-title":"Conference on Health, Inference, and Learning","first-page":"248","article-title":"MedMCQA: a large-scale multi-subject multi-choice dataset for medical domain question answering","author":"Pal","year":"2022"},{"key":"10.1016\/j.inffus.2026.104386_bib0146","doi-asserted-by":"crossref","first-page":"3867","DOI":"10.52202\/075280-0170","article-title":"EHRXQA: a multi-modal question answering dataset for electronic health records with chest X-ray images","volume":"36","author":"Bae","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0147","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.inffus.2026.104386_bib0148","first-page":"25278","article-title":"LAION-5B: an open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0149","unstructured":"L. Zhao, W. Zeng, X. Shi, H. Zhou, D. Hao, Y. Lin, Aqulia-Med LLM: pioneering full-process open-source medical language models, arXiv preprint arXiv: 2406.12182(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0150","unstructured":"J. Wei, Z. Meng, Z. Xiao, T. Hu, Y. Feng, Z. Zhou, J. Wu, Z. Liu, MedEthicsQA: a comprehensive question answering benchmark for medical ethics evaluation of LLMs, arXiv preprint arXiv: 2506.22808(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0151","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"19368","article-title":"Zhongjing: enhancing the chinese medical capabilities of large language model through expert feedback and real-world multi-turn dialogue","volume":"38","author":"Yang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0152","unstructured":"Z. Yu, Y. Li, J. Kim, K. Huang, Y. Luo, M. Wang, Deep reinforcement learning for cost-effective medical diagnosis, arXiv preprint arXiv: 2302.10261(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0153","unstructured":"Y.-F. Zhang, T. Yu, H. Tian, C. Fu, P. Li, J. Zeng, W. Xie, Y. Shi, H. Zhang, J. Wu, et al., MM-RLHF: the next step forward in multimodal llm alignment, arXiv preprint arXiv: 2502.10391(2025a)."},{"key":"10.1016\/j.inffus.2026.104386_bib0154","series-title":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"3718","article-title":"LongReward: improving long-context large language models with ai feedback","author":"Zhang","year":"2025"},{"key":"10.1016\/j.inffus.2026.104386_bib0155","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"22170","article-title":"OmniMedVQA: a new large-scale comprehensive evaluation benchmark for medical LVLM","author":"Hu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0156","unstructured":"J. Chen, Z. Cai, K. Ji, X. Wang, W. Liu, R. Wang, J. Hou, B. Wang, HuatuoGPT-o1, towards medical complex reasoning with LLMs, arXiv preprint arXiv: 2412.18925(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0157","unstructured":"Y. Zhang, Z. Chang, W. Cai, M. Ren, K. Yuan, Y. Sun, Z. Ding, IIMedGPT: promoting large language model capabilities of medical tasks by efficient human preference alignment, arXiv preprint arXiv: 2501.02869(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0158","first-page":"53728","article-title":"Direct preference optimization: your language model is secretly a reward model","volume":"36","author":"Rafailov","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0159","doi-asserted-by":"crossref","DOI":"10.1016\/j.ejrad.2025.111984","article-title":"Aligning large language models with radiologists by reinforcement learning from AI feedback for chest CT reports","volume":"184","author":"Yang","year":"2025","journal-title":"Eur. J. Radiol."},{"key":"10.1016\/j.inffus.2026.104386_bib0160","doi-asserted-by":"crossref","first-page":"96449","DOI":"10.52202\/079017-3057","article-title":"Biomedical visual instruction tuning with clinician preference alignment","volume":"37","author":"Cui","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0161","doi-asserted-by":"crossref","first-page":"226","DOI":"10.1038\/s41746-023-00952-2","article-title":"A medical multimodal large language model for future pandemics","volume":"6","author":"Liu","year":"2023","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0162","unstructured":"S. Wang, S. Zhang, J. Zhang, R. Hu, X. Li, T. Zhang, J. Li, F. Wu, G. Wang, E. Hovy, Reinforcement learning enhanced LLMs: a survey, arXiv preprint arXiv: 2412.10400(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0163","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"20052","article-title":"Self-training large language and vision assistant for medical question answering","author":"Sun","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0164","unstructured":"K. Zhu, P. Xia, Y. Li, H. Zhu, S. Wang, H. Yao, MMedPO: aligning medical vision-language models with clinical-aware multimodal preference optimization, arXiv preprint arXiv: 2412.06141(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0165","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0166","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.130633","article-title":"CLARIFID: improving radiology report generation by reinforcing clinically accurate impressions and enforcing detailed findings","volume":"303","author":"Lee","year":"2026","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.inffus.2026.104386_bib0167","unstructured":"T. Moskovitz, A.K. Singh, D.J. Strouse, T. Sandholm, R. Salakhutdinov, A.D. Dragan, S. McAleer, Confronting reward model overoptimization with constrained RLHF, arXiv preprint arXiv: 2310.04373(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0168","doi-asserted-by":"crossref","DOI":"10.2196\/76048","article-title":"Fine-tuning methods for large language models in clinical medicine by supervised fine-tuning and direct preference optimization: comparative evaluation","volume":"27","author":"Savage","year":"2025","journal-title":"J. Med. Internet Res."},{"issue":"7972","key":"10.1016\/j.inffus.2026.104386_bib0169","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.inffus.2026.104386_bib0170","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1038\/s41746-025-01533-1","article-title":"Me-LLaMA: foundation large language models for medical applications","volume":"8","author":"Xie","year":"2025","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0171","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"12799","article-title":"On the effectiveness of parameter-efficient fine-tuning","volume":"37","author":"Fu","year":"2023"},{"issue":"2","key":"10.1016\/j.inffus.2026.104386_bib0172","first-page":"3","article-title":"Lora: low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"10.1016\/j.inffus.2026.104386_bib0173","unstructured":"J. He, P. Li, G. Liu, G. He, Z. Chen, S. Zhong, PeFoMed: parameter efficient fine-tuning of multimodal large language models for medical imaging, arXiv preprint arXiv: 2401.02797(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0174","doi-asserted-by":"crossref","first-page":"773","DOI":"10.1038\/s41746-025-02139-3","article-title":"Enhancing privacy-preserving deployable large language models for perioperative complication detection: a targeted strategy with LoRA fine-tuning","volume":"8","author":"Gao","year":"2025","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0175","series-title":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","first-page":"3045","article-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.inffus.2026.104386_bib0176","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2024.104630","article-title":"Model tuning or prompt tuning? A study of large language models for clinical concept and relation extraction","volume":"153","author":"Peng","year":"2024","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.inffus.2026.104386_bib0177","doi-asserted-by":"crossref","DOI":"10.1016\/j.jbi.2024.104606","article-title":"SPeC: a soft prompt-based calibration on performance variability of large language model in clinical notes summarization","volume":"151","author":"Chuang","year":"2024","journal-title":"J. Biomed. Inf."},{"key":"10.1016\/j.inffus.2026.104386_bib0178","series-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","first-page":"4582","article-title":"Prefix-tuning: optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.inffus.2026.104386_bib0179","series-title":"The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks","first-page":"449","article-title":"RadAdapt: radiology report summarization via lightweight domain adaptation of large language models","author":"Van Veen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104386_bib0180","series-title":"International Conference on Machine Learning","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","author":"Houlsby","year":"2019"},{"key":"10.1016\/j.inffus.2026.104386_bib0181","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"22294","article-title":"MedAdapter: efficient test-time adaptation of large language models towards medical reasoning","author":"Shi","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0182","series-title":"2024 IEEE International Symposium on Biomedical Imaging (ISBI)","first-page":"1","article-title":"MAKEN: improving medical report generation with adapter tuning and knowledge enhancement in vision-language foundation models","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0183","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations","first-page":"46","article-title":"AdapterHub: a framework for adapting transformers","author":"Pfeiffer","year":"2020"},{"key":"10.1016\/j.inffus.2026.104386_bib0184","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0185","series-title":"Language Gamification-NeurIPS 2024 Workshop","article-title":"On reward functions for self-improving chain-of-thought reasoning without supervised datasets (abridged version)","author":"Foster","year":"2024"},{"key":"#cr-split#-10.1016\/j.inffus.2026.104386_bib0186.1","unstructured":"Z. Shao, P. Wang, Q. Zhu, R. Xu, J. Song, X. Bi, H. Zhang, M. Zhang, Y.K. Li, Y. Wu, et al., DeepSeekMath: pushing the limits of mathematical reasoning in open language models, 2024, 2"},{"key":"#cr-split#-10.1016\/j.inffus.2026.104386_bib0186.2","unstructured":"(3) (2024) 5. URL https:\/\/arxiv.org\/abs\/2402.03300."},{"key":"10.1016\/j.inffus.2026.104386_bib0187","unstructured":"A. Kazemnejad, M. Aghajohari, E. Portelance, A. Sordoni, S. Reddy, A. Courville, N.L. Roux, VinePPO: refining credit assignment in rl training of LLMs, arXiv preprint arXiv: 2410.01679(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0188","article-title":"Med-R1: reinforcement learning for generalizable medical reasoning in vision-language models","volume":"45","author":"Lai","year":"2026","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"3","key":"10.1016\/j.inffus.2026.104386_bib0189","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0118432","article-title":"The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","volume":"10","author":"Saito","year":"2015","journal-title":"PLoS ONE"},{"key":"10.1016\/j.inffus.2026.104386_bib0190","series-title":"Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics","first-page":"311","article-title":"BLEU: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002"},{"key":"10.1016\/j.inffus.2026.104386_bib0191","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: a package for automatic evaluation of summaries","author":"Lin","year":"2004"},{"key":"10.1016\/j.inffus.2026.104386_bib0192","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4566","article-title":"CIDEr: consensus-based image description evaluation","author":"Vedantam","year":"2015"},{"key":"10.1016\/j.inffus.2026.104386_bib0193","series-title":"Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization","first-page":"65","article-title":"METEOR: an automatic metric for MT evaluation with improved correlation with human judgments","author":"Banerjee","year":"2005"},{"key":"10.1016\/j.inffus.2026.104386_bib0194","series-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)","first-page":"1500","article-title":"Combining automatic labelers and expert annotations for accurate radiology report labeling using BERT","author":"Smit","year":"2020"},{"issue":"9","key":"10.1016\/j.inffus.2026.104386_bib0195","doi-asserted-by":"crossref","DOI":"10.1016\/j.patter.2023.100802","article-title":"Evaluating progress in automatic chest x-ray radiology report generation","volume":"4","author":"Yu","year":"2023","journal-title":"Patterns"},{"key":"10.1016\/j.inffus.2026.104386_bib0196","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/s41746-025-02208-7","article-title":"Automating expert-level medical reasoning evaluation of large language models","volume":"9","author":"Zhou","year":"2025","journal-title":"NPJ Digital Med."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0197","doi-asserted-by":"crossref","first-page":"258","DOI":"10.1038\/s41746-024-01258-7","article-title":"A framework for human evaluation of large language models in healthcare derived from literature review","volume":"7","author":"Tam","year":"2024","journal-title":"NPJ Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0198","article-title":"A technology selection tool applying multiple criteria decision analysis for virtual care implementation","volume":"3","author":"Deason","year":"2025","journal-title":"Mayo Clin. Proc. Digital Health"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0199","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1038\/s41746-025-01900-y","article-title":"A practical framework for appropriate implementation and review of artificial intelligence (FAIR-AI) in healthcare","volume":"8","author":"Wells","year":"2025","journal-title":"NPJ Digital Med."},{"issue":"11","key":"10.1016\/j.inffus.2026.104386_bib0200","doi-asserted-by":"crossref","first-page":"e693","DOI":"10.1016\/S2589-7500(21)00216-8","article-title":"Evaluation of artificial intelligence on a reference standard based on subjective interpretation","volume":"3","author":"Chen","year":"2021","journal-title":"Lancet Digital Health"},{"key":"10.1016\/j.inffus.2026.104386_bib0201","doi-asserted-by":"crossref","first-page":"71","DOI":"10.58496\/MJAIH\/2023\/014","article-title":"An overview of the evolution and impact of chatbots in modern healthcare services","volume":"2023","author":"Catherine","year":"2023","journal-title":"Mesopotamian J. Artif. Intell. Healthcare"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0202","doi-asserted-by":"crossref","first-page":"6","DOI":"10.1038\/s44401-024-00011-2","article-title":"Current and future state of evaluation of large language models for medical summarization tasks","volume":"2","author":"Croxford","year":"2025","journal-title":"npj Health Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0203","article-title":"Clinical large language model evaluation by expert review (CLEVER): framework development and validation","volume":"4","author":"Kocaman","year":"2025","journal-title":"JMIR AI"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0204","doi-asserted-by":"crossref","first-page":"3","DOI":"10.3390\/diagnostics16010003","article-title":"Evaluating medical text summaries using automatic evaluation metrics and LLM-as-a-judge approach: a pilot study","volume":"16","author":"Vasilev","year":"2025","journal-title":"Diagnostics"},{"key":"10.1016\/j.inffus.2026.104386_bib0205","doi-asserted-by":"crossref","DOI":"10.3389\/fdgth.2025.1653631","article-title":"A systematic review of ethical considerations of large language models in healthcare and medicine","volume":"7","author":"Fareed","year":"2025","journal-title":"Front. Digital Health"},{"key":"10.1016\/j.inffus.2026.104386_bib0206","doi-asserted-by":"crossref","DOI":"10.2196\/76571","article-title":"Considerations for patient privacy of large language models in health care: scoping review","volume":"27","author":"Zhong","year":"2025","journal-title":"J. Med. Internet Res."},{"key":"10.1016\/j.inffus.2026.104386_bib0207","unstructured":"S. Xu, L. Yang, C. Kelly, M. Sieniek, T. Kohlberger, M. Ma, W.-H. Weng, A. Kiraly, S. Kazemzadeh, Z. Melamed, et al., ELIXR: towards a general purpose X-ray artificial intelligence system through alignment of large language models and radiology vision encoders, arXiv preprint arXiv: 2308.01317(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0208","doi-asserted-by":"crossref","DOI":"10.3389\/fdgth.2025.1659134","article-title":"Large language models in real-world clinical workflows: a systematic review of applications and implementation","volume":"7","author":"Artsi","year":"2025","journal-title":"Front. Digital Health"},{"issue":"2","key":"10.1016\/j.inffus.2026.104386_bib0209","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1038\/s41591-024-03302-1","article-title":"Collaboration between clinicians and vision\u2013language models in radiology report generation","volume":"31","author":"Tanno","year":"2025","journal-title":"Nat. Med."},{"issue":"8","key":"10.1016\/j.inffus.2026.104386_bib0210","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2025.26021","article-title":"Fidelity of medical reasoning in large language models","volume":"8","author":"Bedi","year":"2025","journal-title":"JAMA Netw. Open"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0211","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1038\/s44401-024-00004-1","article-title":"Retrieval-augmented generation for generative artificial intelligence in health care","volume":"2","author":"Yang","year":"2025","journal-title":"npj Health Syst."},{"issue":"3","key":"10.1016\/j.inffus.2026.104386_bib0212","doi-asserted-by":"crossref","first-page":"2598","DOI":"10.1109\/LRA.2025.3535184","article-title":"From decision to action in surgical autonomy: multi-modal large language models for robot-assisted blood suction","volume":"10","author":"Zargarzadeh","year":"2025","journal-title":"IEEE Rob. Autom. Lett."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0213","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s10916-024-02117-4","article-title":"An assessment of an inpatient robotic nurse assistant: a mixed-method study","volume":"48","author":"Lim","year":"2024","journal-title":"J. Med. Syst."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0214","doi-asserted-by":"crossref","first-page":"9377","DOI":"10.1038\/s41467-025-64430-x","article-title":"AgentMD: empowering language agents for risk prediction with large-scale clinical tool learning","volume":"16","author":"Jin","year":"2025","journal-title":"Nat. Commun."},{"issue":"2","key":"10.1016\/j.inffus.2026.104386_bib0215","doi-asserted-by":"crossref","DOI":"10.1093\/bioinformatics\/btae075","article-title":"GeneGPT: augmenting large language models with domain tools for improved access to biomedical information","volume":"40","author":"Jin","year":"2024","journal-title":"Bioinformatics"},{"issue":"10","key":"10.1016\/j.inffus.2026.104386_bib0216","doi-asserted-by":"crossref","first-page":"3394","DOI":"10.1038\/s41591-025-03888-0","article-title":"A personal health large language model for sleep and fitness coaching","volume":"31","author":"Khasentino","year":"2025","journal-title":"Nat. Med."},{"issue":"1143","key":"10.1016\/j.inffus.2026.104386_bib0217","article-title":"Transforming wearable data into personal health insights using large language model agents","volume":"17","author":"Merrill","year":"2026","journal-title":"Nat. Commun."},{"key":"10.1016\/j.inffus.2026.104386_bib0218","unstructured":"Y. Kim, X. Xu, D. McDuff, C. Breazeal, H.W. Park, Health-LLM: large language models for health prediction via wearable sensor data, arXiv preprint arXiv: 2401.06866(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0219","unstructured":"F. Bai, K. Harrigian, J. Stremmel, H. Hassanzadeh, A. Saeedi, M. Dredze, Give me some hard questions: synthetic data generation for clinical QA, arXiv preprint arXiv: 2412.04573(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0220","series-title":"The Fourteenth International Conference on Learning Representations","article-title":"Synthesizing high-quality visual question answering from medical documents with generator-verifier LMMs","author":"Huang","year":"2026"},{"key":"10.1016\/j.inffus.2026.104386_bib0221","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1038\/s43856-025-01283-x","article-title":"Simulated patient systems powered by large language model-based AI agents offer potential for transforming medical education","volume":"6","author":"Yu","year":"2026","journal-title":"Commun. Med."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0222","article-title":"Enhancing medical interview skills through AI-simulated patient interactions: nonrandomized controlled trial","volume":"10","author":"Yamamoto","year":"2024","journal-title":"JMIR Med. Educ."},{"key":"10.1016\/j.inffus.2026.104386_bib0223","series-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing","first-page":"17371","article-title":"MedCoT: medical chain of thought via hierarchical expert","author":"Liu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104386_bib0224","unstructured":"J. Li, G. Skinner, G. Yang, B.R. Quaranto, S.D. Schwaitzberg, P.C.W. Kim, J. Xiong, LLaVA-surg: towards multimodal surgical assistant via structured surgical video learning, arXiv preprint arXiv: 2408.07981(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0225","article-title":"EndoChat: grounded multimodal large language model for endoscopic surgery","volume":"107","author":"Wang","year":"2025","journal-title":"Med. Image Anal."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0226","doi-asserted-by":"crossref","DOI":"10.1002\/aisy.202500255","article-title":"MedVH: toward systematic evaluation of hallucination for large vision language models in the medical context","volume":"8","author":"Gu","year":"2026","journal-title":"Adv. Intell. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0227","unstructured":"L. Wang, Y. Qin, H. Yang, X. Li, Proactive reasoning-with-retrieval framework for medical multimodal large language models, arXiv preprint arXiv: 2510.18303(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0228","unstructured":"Z. Chen, A.H. Cano, A. Romanou, A. Bonnet, K. Matoba, F. Salvi, M. Pagliardini, S. Fan, A. K\u00f6pf, A. Mohtashami, et al., MEDITRON-70B: scaling medical pretraining for large language models, arXiv preprint arXiv: 2311.16079(2023)."},{"key":"10.1016\/j.inffus.2026.104386_bib0229","series-title":"Ethics and Governance of Artificial Intelligence for Health: Large Multi-Modal Models. WHO guidance","author":"Organization","year":"2024"},{"issue":"6","key":"10.1016\/j.inffus.2026.104386_bib0230","doi-asserted-by":"crossref","first-page":"e428","DOI":"10.1016\/S2589-7500(24)00061-X","article-title":"Ethical and regulatory challenges of large language models in medicine","volume":"6","author":"Ong","year":"2024","journal-title":"Lancet Digital Health"},{"key":"10.1016\/j.inffus.2026.104386_bib0231","series-title":"Technical Report","article-title":"Marketing Submission Recommendations for a Predetermined Change Control Plan for Artificial Intelligence-Enabled Device Software Functions","author":"Food","year":"2025"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0232","doi-asserted-by":"crossref","first-page":"252","DOI":"10.1038\/s41746-025-01674-3","article-title":"Rethinking clinical trials for medical AI with dynamic deployments of adaptive systems","volume":"8","author":"Rosenthal","year":"2025","journal-title":"npj Digital Med."},{"key":"10.1016\/j.inffus.2026.104386_bib0233","first-page":"79410","article-title":"MDAgents: an adaptive collaboration of llms for medical decision-making","volume":"37","author":"Kim","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.inffus.2026.104386_bib0234","unstructured":"K. Chen, X. Li, T. Yang, H. Wang, W. Dong, Y. Gao, MDTeamGPT: a self-evolving LLM-based multi-agent framework for multi-disciplinary team medical consultation, arXiv preprint arXiv: 2503.13856(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0235","unstructured":"Y. Feng, J. Wang, L. Zhou, Z. Lei, Y. Li, DoctorAgent-RL: a multi-agent collaborative reinforcement learning system for multi-turn clinical dialogue, arXiv preprint arXiv: 2505.19630(2025)."},{"key":"10.1016\/j.inffus.2026.104386_bib0236","unstructured":"Z. Liu, Y. Wang, S. Vaidya, F. Ruehle, J. Halverson, M. Solja\u010di\u0107, T.Y. Hou, M. Tegmark, KAN: Kolmogorov-arnold networks, arXiv preprint arXiv: 2404.19756(2024)."},{"key":"10.1016\/j.inffus.2026.104386_bib0237","series-title":"First Conference on Language Modeling","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0238","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1038\/s41746-024-01413-0","article-title":"Digital twin assisted surgery, concept, opportunities, and challenges","volume":"8","author":"Asciak","year":"2025","journal-title":"npj Digital Med."},{"issue":"104","key":"10.1016\/j.inffus.2026.104386_bib0239","article-title":"SRT-H: a hierarchical framework for autonomous surgery via language-conditioned imitation learning","volume":"10","author":"Kim","year":"2025","journal-title":"Sci. Rob."},{"key":"10.1016\/j.inffus.2026.104386_bib0240","doi-asserted-by":"crossref","DOI":"10.1145\/3674838","article-title":"TWIN-GPT: digital twins for clinical trials via large language model","author":"Wang","year":"2024","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"issue":"1","key":"10.1016\/j.inffus.2026.104386_bib0241","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1038\/s41540-025-00592-0","article-title":"Enhancing randomized clinical trials with digital twins","volume":"11","author":"Akbarialiabad","year":"2025","journal-title":"npj Syst. Biol. Appl."},{"issue":"4","key":"10.1016\/j.inffus.2026.104386_bib0242","article-title":"Using AI-generated digital twins to boost clinical trial efficiency in Alzheimer\u2019s disease","volume":"11","author":"Wang","year":"2025","journal-title":"Alzheimer\u2019s Dementia Trans. Res. Clin. Interventions"},{"issue":"10","key":"10.1016\/j.inffus.2026.104386_bib0243","doi-asserted-by":"crossref","first-page":"1517","DOI":"10.1093\/jamia\/ocaf127","article-title":"Toward digital twins in the intensive care unit: a medication management case study","volume":"32","author":"Eslami","year":"2025","journal-title":"J. Am. Med. Inf. Assoc."},{"key":"10.1016\/j.inffus.2026.104386_bib0244","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2026.131364","article-title":"A survey on large language models for medical time series","volume":"311","author":"Liu","year":"2026","journal-title":"Expert Syst. Appl."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002654?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526002654?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T11:40:08Z","timestamp":1779190808000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526002654"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":245,"alternative-id":["S1566253526002654"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104386","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Medical multimodal large language models: A survey","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104386","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"104386"}}